update-swiftui-apis

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh pr create) to automate the creation of pull requests. This grants the agent the ability to execute shell commands and interact with the repository's host platform.
  • [PROMPT_INJECTION]: The workflow involves fetching and processing content from external sources which could contain malicious instructions designed to influence the agent's behavior (Indirect Prompt Injection).
  • Ingestion points: The agent calls fetchAppleDocumentation, fetchAppleVideoTranscript, and fetchExternalDocumentation (specified in SKILL.md) to process external documentation and video transcripts.
  • Boundary markers: Absent. There are no explicit instructions or delimiters provided to ensure the agent ignores natural language instructions that might be embedded within the fetched documentation content.
  • Capability inventory: The agent has the capability to write to the local filesystem (swiftui-expert-skill/references/latest-apis.md) and execute shell commands (gh pr create).
  • Sanitization: Absent. The skill does not describe any validation or sanitization of the fetched content before using it to generate the pull request body or update reference files.
  • [DATA_EXPOSURE]: The skill requires access to local repository files and relies on GitHub credentials being available in the environment to perform gh commands, which involves handling sensitive authorization tokens.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 08:47 PM
Security Audit — agent-trust-hub — update-swiftui-apis